TEST #595 RESULTS
04/08/2025 - 12:16 PM
ACCELERATOR
MODEL
17.7
tokens/s
generation
6.89
sec
time to first token
185
tokens/s
prompt
78
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:11:02 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
209
tokens/s
18.7
tokens/s
4.95
sec
pp4096+tg256
184
tokens/s
15.1
tokens/s
22.29
sec
pp2048+tg256
201
tokens/s
17.3
tokens/s
10.24
sec
pp2048+tg768
201
tokens/s
16.9
tokens/s
10.26
sec
pp1024+tg1024
204
tokens/s
18.1
tokens/s
5.08
sec
pp1280+tg3072
195
tokens/s
16.5
tokens/s
6.61
sec
pp384+tg1152
203
tokens/s
18.8
tokens/s
1.94
sec
pp64+tg1024
182
tokens/s
19.4
tokens/s
402
ms
pp16+tg1536
83
tokens/s
18.9
tokens/s
243
ms